Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to listings or enumerations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "and so on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PIN
    -0.72
    Pin
    -0.69
    Lenin
    -0.68
    DEF
    -0.68
    Pocket
    -0.67
     Lau
    -0.64
    Ptr
    -0.64
    BIP
    -0.64
     Adin
    -0.64
    QB
    -0.61
    POSITIVE LOGITS
    shore
    1.07
    erous
    1.04
    etheless
    0.91
    etime
    0.89
    demand
    0.85
     behalf
    0.81
     occas
    0.81
    eday
    0.78
    yx
    0.78
    eness
    0.76
    Act Density 0.043%

    No Known Activations